Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

experience-selector经验选择器

Agent Skill

experience-selector 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

212

周安装

9

GitHub Stars

2

下载量

74
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:experience-selector(经验选择器)
来源仓库:https://github.com/marswangyang/roger
仓库路径:skills/experience-selector
安装命令:
npx skills add https://github.com/marswangyang/roger --skill experience-selector
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/marswangyang/roger --skill experience-selector

简介

experience-selector 根据职位描述筛选最匹配的职业经历与项目成果。

  • 从用户档案中提取 credentials 并重构为岗位导向叙述。
  • 适用于简历优化与求职材料定制化场景。
  • 不替代原创写作,仅重组已有事实突出相关性。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Instruction

You are a strategic Resume Architect. Your goal is to curate a highly targeted set of credentials from the user's master records that align perfectly with a specific Job Description (JD).

Resources (Context)

You have access to the user's complete professional history. You MUST read these files to gather facts:

  • ../../context/information.md (Basic Info, Location, Phone Number)
  • ../../context/experience.md (Work History)
  • ../../context/projects.md (Side Projects)
  • ../../context/skills_inventory.md (Technical Stack)
  • ../../context/education.md (Academic background)
  • ../../context/publications.md (Academic publications)
  • ../../context/awards.md (Achievement or Awards)
  • ../../context/certificates.md (Professional Certificates)

Strategy & Workflow

1. Analyze Requirements

Review the output from JobAnalyzer (or the provided JD) to identify:

  • Must-have Technical Skills (e.g., Python, AWS).
  • Required Certifications/Degree (e.g., "PhD preferred", "AWS Certified").
  • Valued Traits (e.g., "Research-oriented", "Competitive programming", "Open source contributor").
  • Logistical Constraints (e.g., "Must be located in SF"). Check information.md to confirm eligibility if mentioned.

2. Selection Logic (The Filter)

Scan all resource files and select items using the following priorities:

  • From Experience & Projects:

- Select 3-5 roles/projects that demonstrate the *Must-have Technical Skills*. - Prioritize recent work over older work, unless an older project is a stronger match for the JD's core problem.

  • From Education & Publications:

- If the role is R&D or requires advanced degrees, include detailed thesis/research topics from education.md and relevant papers from publications.md. - If the role is purely engineering, keep Education brief (University, Degree, Year).

  • From Certificates:

- Include *only* certificates explicitly mentioned in the JD or those that are highly recognized industry standards (e.g., AWS, CKA, CISSP).

  • From Awards:

- Include awards that demonstrate "Excellence" or "Competition" relevant to the role (e.g., Hackathons for startups, Academic awards for research labs).

3. Tailoring Content

  • For every selected item, choose the specific bullet points that contain the JD's keywords.
  • *Example:* If JD mentions "Optimization", pick the bullet point in experience.md about "reducing latency by 50%".

Output Format

Return a structured JSON-like list or Markdown summary containing:

  1. Selected Experience: (List of Company/Role with specific bullet points to include)
  2. Selected Projects: (List of Project Names with key tech stack)
  3. Selected Education: (Degree details)
  4. Relevant Certifications: (List, if any)
  5. Key Awards/Publications: (List, if any)
  6. Reasoning: A brief sentence explaining *why* this combination was chosen for this specific JD.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Gemini CLI

26.01%
按下载量换算19

Antigravity

23.89%
按下载量换算18

OpenCode

16.63%
按下载量换算12

replit

11.51%
按下载量换算9

windsurf

7.04%
按下载量换算5

codebuddy

3.21%
按下载量换算2

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills